From: John Arbash Meinel <john@arbash-meinel.com>
To: Vig, Sandor (G/FI-2) <Sandor.Vig@audi.hu>
Cc: 'pgsql-performance@postgresql.org' <pgsql-performance@postgresql.org>
Subject: Re: multi billion row tables: possible or insane?
Date: Tue, 01 Mar 2005 09:52:12 -0600
Message-ID: <42248FAC.2010103@arbash-meinel.com> (raw)
In-Reply-To: <977921B17B2F2048AA5AAE9B4CBB713E01423D75@huaudigs0035.audi.de>
References: <977921B17B2F2048AA5AAE9B4CBB713E01423D75@huaudigs0035.audi.de>
Vig, Sandor (G/FI-2) wrote:
>385 transaction/sec?
>
>fsync = false
>
>risky but fast.
>
>
I think with a dedicated RAID10 for pg_xlog (or possibly a battery
backed up ramdisk), and then a good amount of disks in a bulk RAID10 or
possibly a good partitioning of the db across multiple raids, you could
probably get a good enough tps.
But you're right, fsync=false could certainly give you the performance,
though a power outage means potential *real* corruption. Not just
missing transactions, but duplicated rows, all sorts of ugliness.
John
=:->
Attachments:
signature.asc (application/pgp-signature, 252B) download
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: john@arbash-meinel.com, Sandor.Vig@audi.hu
Subject: Re: multi billion row tables: possible or insane?
In-Reply-To: <42248FAC.2010103@arbash-meinel.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox